irds/msmarco-document-v2_trec-dl-2020_judged

---
pretty_name: '`msmarco-document-v2/trec-dl-2020/judged`'
viewer: false
source_datasets: ['irds/msmarco-document-v2', 'irds/msmarco-document-v2_trec-dl-2020']
task_categories:
- text-retrieval
---

# Dataset Card for `msmarco-document-v2/trec-dl-2020/judged`

The `msmarco-document-v2/trec-dl-2020/judged` dataset, provided by the [ir-datasets](https://ir-datasets.com/) package.
For more information about the dataset, see the [documentation](https://ir-datasets.com/msmarco-document-v2#msmarco-document-v2/trec-dl-2020/judged).

# Data

This dataset provides:
- `queries` (i.e., topics); count=45

- For `docs`, use [`irds/msmarco-document-v2`](https://huggingface.co/datasets/irds/msmarco-document-v2)
- For `qrels`, use [`irds/msmarco-document-v2_trec-dl-2020`](https://huggingface.co/datasets/irds/msmarco-document-v2_trec-dl-2020)

## Usage

```python
from datasets import load_dataset

queries = load_dataset('irds/msmarco-document-v2_trec-dl-2020_judged', 'queries')
for record in queries:
record # {'query_id': ..., 'text': ...}

```

Note that calling `load_dataset` will download the dataset (or provide access instructions when it's not public) and make a copy of the
data in 🤗 Dataset format.

## Citation Information

```
@inproceedings{Craswell2020TrecDl,
title={Overview of the TREC 2020 deep learning track},
author={Nick Craswell and Bhaskar Mitra and Emine Yilmaz and Daniel Campos},
booktitle={TREC},
year={2020}
}
@inproceedings{Bajaj2016Msmarco,
title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset},
author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang},
booktitle={InCoCo@NIPS},
year={2016}
}
```

原始信息汇总

数据集概述

数据集名称

msmarco-document-v2/trec-dl-2020/judged

数据集来源

• 主要来源：irds/msmarco-document-v2
• 相关数据：irds/msmarco-document-v2_trec-dl-2020

数据集内容

• 查询（queries）: 数量为45。
• 文档（docs）: 使用irds/msmarco-document-v2数据集。
• 查询关系（qrels）: 使用irds/msmarco-document-v2_trec-dl-2020数据集。

数据集任务类别

• 文本检索（text-retrieval）

数据集使用示例

python from datasets import load_dataset

queries = load_dataset(irds/msmarco-document-v2_trec-dl-2020_judged, queries) for record in queries: record # {query_id: ..., text: ...}

引用信息

@inproceedings{Craswell2020TrecDl, title={Overview of the TREC 2020 deep learning track}, author={Nick Craswell and Bhaskar Mitra and Emine Yilmaz and Daniel Campos}, booktitle={TREC}, year={2020} } @inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }

搜集汇总

背景与挑战

背景概述

该数据集是irds/msmarco-document-v2_trec-dl-2020_judged，专门用于文本检索任务，包含45个查询（主题）。它基于MS MARCO文档集和TREC 2020深度学习竞赛，用于评估信息检索系统的性能，其中文档和相关判断需分别引用其他irds数据集。